ML Market Map — China A-Share Clusters for 2026-07-16

A daily unsupervised machine-learning read of the China A-Share market: 5,442 stocks grouped into 6 consensus clusters (KMeans + Gaussian-mixture + hierarchical, over robust-scaled PCA features) for 2026-07-16. Descriptive, not predictive — there is no buy or sell signal. Research, not investment advice.

Markets: US Equity · China A-Share · Japan Equity · Hong Kong Equity · Taiwan Equity · Korea Equity · UK Equity · India Equity

Today's clusters

• high margin · low volatility (1y) · low idio vol — 1,895 names; mostly Industrials; drivers: profit margin (+0.43), rv 252 (−0.42), residual vol 252 d (−0.39)
• high downside vol · high turnover · high volatility (3m) — 1,046 names; mostly Industrials; drivers: vol of vol 63 (+1.10), downside vol 63 (+0.98), turnover to mcap (+0.72)
• strong 1y momentum · rising (3m) · high turnover — 757 names; mostly Technology; drivers: ret 252d (+2.73), ret 126d (+2.20), ret 63d (+1.79)
• expensive (low E/P) · low margin · falling earnings — 737 names; mostly Industrials; drivers: val ep z (−2.33), profit margin (−2.10), ni growth (−1.36)
• high leverage — 643 names; mostly Industrials; drivers: cfo growth (+1.75), leverage debt to mcap (+0.43), ni growth (+0.34)
• high leverage · cheap (high B/P) · high cash yield — 364 names; mostly Industrials; drivers: leverage debt to mcap (+4.00), val bp z (+1.62), val cfop z (+1.60)

Machine-readable data (free, read-only JSON)

The full map, per-ticker cluster assignments with confidence and anomaly scores, and PCA structure are published as open JSON for automated and AI-analyst consumption:

• /api/ml/latest?market=cn — clusters, names, sector mix, representative tickers, top features
• /api/ml/tickers?market=cn — per-ticker cluster, confidence, anomaly score, day-over-day migration, tenure
• /api/ml/pca?market=cn — PCA components, explained variance, feature loadings

Descriptive market-structure research only. Unsupervised clustering finds structure, not direction; a tight cluster or an anomaly is a starting point for research, never a trade signal.